ClawHub
Back to skill

Security audit

Knowledge Graph - Graph Constraint Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local knowledge-graph constraint helper with no evidence of hidden access, persistence, or unsafe behavior.

This appears safe to install for local schema-design assistance. Treat the generated constraints as templates and review or test them before applying them to a real graph database, especially the SHACL output and any production Cypher statements.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The module docstring and manifest describe broader constraint generation for RDF/OWL ontologies and property graph models, including structural, semantic, and property constraints. In practice, the implementation only supports a few hardcoded categories such as unique, required, cardinality, and domain/range constraints, and the executable path demonstrates only property-graph examples; there is no general property-constraint synthesis logic beyond manual additions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The docstring states this method generates SHACL shapes for RDF/OWL validation, implying usable validation output. However, the emitted shapes reference ':Shape', ':Label', and ':property' terms without adding a matching prefix declaration, so the output is not self-consistent as written and does not fully match the documented intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.